/*
* Check if this packet is complete.
* Returns NULL on failure by any reason, and pointer
* to current nexthdr field in reassembled frame.
*
* It is called with locked fq, and caller must check that
* queue is eligible for reassembly i.e. it is not COMPLETE,
* the last and the first frames arrived and all the bits are here.
*/
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
struct net_device *dev)
{
struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
struct sk_buff *fp, *head = fq->q.fragments;
int payload_len;
unsigned int nhoff;
fq_kill(fq);
/* Make the one we just received the head. */
if (prev) {
head = prev->next;
fp = skb_clone(head, GFP_ATOMIC);
if (!fp)
goto out_oom;
fp->next = head->next;
if (!fp->next)
fq->q.fragments_tail = fp;
prev->next = fp;
skb_morph(head, fq->q.fragments);
head->next = fq->q.fragments->next;
kfree_skb(fq->q.fragments);
fq->q.fragments = head;
}
WARN_ON(head == NULL);
WARN_ON(FRAG6_CB(head)->offset != 0);
/* Unfragmented part is taken from the first segment. */
payload_len = ((head->data - skb_network_header(head)) -
sizeof(struct ipv6hdr) + fq->q.len -
sizeof(struct frag_hdr));
if (payload_len > IPV6_MAXPLEN)
goto out_oversize;
/* Head of list must not be cloned. */
if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC))
goto out_oom;
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments. */
if (skb_has_frags(head)) {
struct sk_buff *clone;
int i, plen = 0;
if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL)
goto out_oom;
clone->next = head->next;
head->next = clone;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
skb_frag_list_init(head);
for (i=0; i<skb_shinfo(head)->nr_frags; i++)
plen += skb_shinfo(head)->frags[i].size;
clone->len = clone->data_len = head->data_len - plen;
head->data_len -= clone->len;
head->len -= clone->len;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
atomic_add(clone->truesize, &fq->q.net->mem);
}
/* We have to remove fragment header from datagram and to relocate
* header in order to calculate ICV correctly. */
nhoff = fq->nhoffset;
skb_network_header(head)[nhoff] = skb_transport_header(head)[0];
memmove(head->head + sizeof(struct frag_hdr), head->head,
(head->data - head->head) - sizeof(struct frag_hdr));
head->mac_header += sizeof(struct frag_hdr);
head->network_header += sizeof(struct frag_hdr);
skb_shinfo(head)->frag_list = head->next;
skb_reset_transport_header(head);
skb_push(head, head->data - skb_network_header(head));
for (fp=head->next; fp; fp = fp->next) {
head->data_len += fp->len;
head->len += fp->len;
if (head->ip_summed != fp->ip_summed)
head->ip_summed = CHECKSUM_NONE;
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
}
atomic_sub(head->truesize, &fq->q.net->mem);
head->next = NULL;
head->dev = dev;
head->tstamp = fq->q.stamp;
ipv6_hdr(head)->payload_len = htons(payload_len);
IP6CB(head)->nhoff = nhoff;
/* Yes, and fold redundant checksum back. 8) */
if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_partial(skb_network_header(head),
skb_network_header_len(head),
head->csum);
rcu_read_lock();
IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
rcu_read_unlock();
fq->q.fragments = NULL;
fq->q.fragments_tail = NULL;
return 1;
out_oversize:
if (net_ratelimit())
printk(KERN_DEBUG "ip6_frag_reasm: payload len = %d\n", payload_len);
goto out_fail;
out_oom:
if (net_ratelimit())
printk(KERN_DEBUG "ip6_frag_reasm: no memory for reassembly\n");
out_fail:
rcu_read_lock();
IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
rcu_read_unlock();
return -1;
}
int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
int offset, int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6,
struct rt6_info *rt, unsigned int flags, int dontfrag)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_cork *cork;
struct sk_buff *skb, *skb_prev = NULL;
unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
int exthdrlen;
int dst_exthdrlen;
int hh_len;
int copy;
int err;
int offset = 0;
int csummode = CHECKSUM_NONE;
__u8 tx_flags = 0;
if (flags&MSG_PROBE)
return 0;
cork = &inet->cork.base;
if (skb_queue_empty(&sk->sk_write_queue)) {
/*
* setup for corking
*/
if (opt) {
if (WARN_ON(np->cork.opt))
return -EINVAL;
np->cork.opt = kzalloc(opt->tot_len, sk->sk_allocation);
if (unlikely(np->cork.opt == NULL))
return -ENOBUFS;
np->cork.opt->tot_len = opt->tot_len;
np->cork.opt->opt_flen = opt->opt_flen;
np->cork.opt->opt_nflen = opt->opt_nflen;
np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt,
sk->sk_allocation);
if (opt->dst0opt && !np->cork.opt->dst0opt)
return -ENOBUFS;
np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt,
sk->sk_allocation);
if (opt->dst1opt && !np->cork.opt->dst1opt)
return -ENOBUFS;
np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt,
sk->sk_allocation);
if (opt->hopopt && !np->cork.opt->hopopt)
return -ENOBUFS;
np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt,
sk->sk_allocation);
if (opt->srcrt && !np->cork.opt->srcrt)
return -ENOBUFS;
/* need source address above miyazawa*/
}
dst_hold(&rt->dst);
cork->dst = &rt->dst;
inet->cork.fl.u.ip6 = *fl6;
np->cork.hop_limit = hlimit;
np->cork.tclass = tclass;
if (rt->dst.flags & DST_XFRM_TUNNEL)
mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
rt->dst.dev->mtu : dst_mtu(&rt->dst);
else
mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
rt->dst.dev->mtu : dst_mtu(rt->dst.path);
if (np->frag_size < mtu) {
if (np->frag_size)
mtu = np->frag_size;
}
cork->fragsize = mtu;
if (dst_allfrag(rt->dst.path))
cork->flags |= IPCORK_ALLFRAG;
cork->length = 0;
sk->sk_sndmsg_page = NULL;
sk->sk_sndmsg_off = 0;
exthdrlen = (opt ? opt->opt_flen : 0);
length += exthdrlen;
transhdrlen += exthdrlen;
dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len;
} else {
rt = (struct rt6_info *)cork->dst;
fl6 = &inet->cork.fl.u.ip6;
opt = np->cork.opt;
transhdrlen = 0;
exthdrlen = 0;
dst_exthdrlen = 0;
mtu = cork->fragsize;
}
orig_mtu = mtu;
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
(opt ? opt->opt_nflen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
if (cork->length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
ipv6_local_error(sk, EMSGSIZE, fl6, mtu-exthdrlen);
return -EMSGSIZE;
}
}
/* For UDP, check if TX timestamp is enabled */
if (sk->sk_type == SOCK_DGRAM) {
err = sock_tx_timestamp(sk, &tx_flags);
if (err)
goto error;
}
/*
* Let's try using as much space as possible.
* Use MTU if total length of the message fits into the MTU.
* Otherwise, we need to reserve fragment header and
* fragment alignment (= 8-15 octects, in total).
*
* Note that we may need to "move" the data from the tail of
* of the buffer to the new fragment when we split
* the message.
*
* FIXME: It may be fragmented into multiple chunks
* at once if non-fragmentable extension headers
* are too large.
* --yoshfuji
*/
if ((length > mtu) && dontfrag && (sk->sk_protocol == IPPROTO_UDP ||
sk->sk_protocol == IPPROTO_RAW)) {
ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen);
return -EMSGSIZE;
}
skb = skb_peek_tail(&sk->sk_write_queue);
cork->length += length;
if (((length > mtu) ||
(skb && skb_has_frags(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
(rt->dst.dev->features & NETIF_F_UFO)) {
err = ip6_ufo_append_data(sk, getfrag, from, length,
hh_len, fragheaderlen,
transhdrlen, mtu, flags, rt);
if (err)
goto error;
return 0;
}
if (!skb)
goto alloc_new_skb;
while (length > 0) {
/* Check if the remaining data fits into current packet. */
copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
if (copy < length)
copy = maxfraglen - skb->len;
if (copy <= 0) {
char *data;
unsigned int datalen;
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
alloc_new_skb:
/* There's no room in the current skb */
if (skb)
fraggap = skb->len - maxfraglen;
else
fraggap = 0;
/* update mtu and maxfraglen if necessary */
if (skb == NULL || skb_prev == NULL)
ip6_append_data_mtu(&mtu, &maxfraglen,
fragheaderlen, skb, rt,
orig_mtu);
skb_prev = skb;
/*
* If remaining data exceeds the mtu,
* we know we need more fragment(s).
*/
datalen = length + fraggap;
if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
alloclen = mtu;
else
alloclen = datalen + fragheaderlen;
alloclen += dst_exthdrlen;
if (datalen != length + fraggap) {
/*
* this is not the last fragment, the trailer
* space is regarded as data space.
*/
datalen += rt->dst.trailer_len;
}
alloclen += rt->dst.trailer_len;
fraglen = datalen + fragheaderlen;
/*
* We just reserve space for fragment header.
* Note: this may be overallocation if the message
* (without MSG_MORE) fits into the MTU.
*/
alloclen += sizeof(struct frag_hdr);
if (transhdrlen) {
skb = sock_alloc_send_skb(sk,
alloclen + hh_len,
(flags & MSG_DONTWAIT), &err);
} else {
skb = NULL;
if (atomic_read(&sk->sk_wmem_alloc) <=
2 * sk->sk_sndbuf)
skb = sock_wmalloc(sk,
alloclen + hh_len, 1,
sk->sk_allocation);
if (unlikely(skb == NULL))
err = -ENOBUFS;
else {
/* Only the initial fragment
* is time stamped.
*/
tx_flags = 0;
}
}
if (skb == NULL)
goto error;
/*
* Fill in the control structures
*/
skb->ip_summed = csummode;
skb->csum = 0;
/* reserve for fragmentation and ipsec header */
skb_reserve(skb, hh_len + sizeof(struct frag_hdr) +
dst_exthdrlen);
if (sk->sk_type == SOCK_DGRAM)
skb_shinfo(skb)->tx_flags = tx_flags;
/*
* Find where to start putting bytes
*/
data = skb_put(skb, fraglen);
skb_set_network_header(skb, exthdrlen);
data += fragheaderlen;
skb->transport_header = (skb->network_header +
fragheaderlen);
if (fraggap) {
skb->csum = skb_copy_and_csum_bits(
skb_prev, maxfraglen,
data + transhdrlen, fraggap, 0);
skb_prev->csum = csum_sub(skb_prev->csum,
skb->csum);
data += fraggap;
pskb_trim_unique(skb_prev, maxfraglen);
}
copy = datalen - transhdrlen - fraggap;
if (copy < 0) {
err = -EINVAL;
kfree_skb(skb);
goto error;
} else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
goto error;
}
offset += copy;
length -= datalen - fraggap;
transhdrlen = 0;
exthdrlen = 0;
dst_exthdrlen = 0;
csummode = CHECKSUM_NONE;
/*
* Put the packet on the pending queue
*/
__skb_queue_tail(&sk->sk_write_queue, skb);
continue;
}
if (copy > length)
copy = length;
if (!(rt->dst.dev->features&NETIF_F_SG)) {
unsigned int off;
off = skb->len;
if (getfrag(from, skb_put(skb, copy),
offset, copy, off, skb) < 0) {
__skb_trim(skb, off);
err = -EFAULT;
goto error;
}
} else {
int i = skb_shinfo(skb)->nr_frags;
skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
struct page *page = sk->sk_sndmsg_page;
int off = sk->sk_sndmsg_off;
unsigned int left;
if (page && (left = PAGE_SIZE - off) > 0) {
if (copy >= left)
copy = left;
if (page != skb_frag_page(frag)) {
if (i == MAX_SKB_FRAGS) {
err = -EMSGSIZE;
goto error;
}
skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0);
skb_frag_ref(skb, i);
frag = &skb_shinfo(skb)->frags[i];
}
} else if(i < MAX_SKB_FRAGS) {
if (copy > PAGE_SIZE)
copy = PAGE_SIZE;
page = alloc_pages(sk->sk_allocation, 0);
if (page == NULL) {
err = -ENOMEM;
goto error;
}
sk->sk_sndmsg_page = page;
sk->sk_sndmsg_off = 0;
skb_fill_page_desc(skb, i, page, 0, 0);
frag = &skb_shinfo(skb)->frags[i];
} else {
err = -EMSGSIZE;
goto error;
}
if (getfrag(from,
skb_frag_address(frag) + skb_frag_size(frag),
offset, copy, skb->len, skb) < 0) {
err = -EFAULT;
goto error;
}
sk->sk_sndmsg_off += copy;
skb_frag_size_add(frag, copy);
skb->len += copy;
skb->data_len += copy;
skb->truesize += copy;
atomic_add(copy, &sk->sk_wmem_alloc);
}
offset += copy;
length -= copy;
}
return 0;
error:
cork->length -= length;
IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
return err;
}
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
struct net_device *dev)
{
struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
struct sk_buff *fp, *head = fq->q.fragments;
int payload_len;
unsigned int nhoff;
fq_kill(fq);
if (prev) {
head = prev->next;
fp = skb_clone(head, GFP_ATOMIC);
if (!fp)
goto out_oom;
fp->next = head->next;
prev->next = fp;
skb_morph(head, fq->q.fragments);
head->next = fq->q.fragments->next;
kfree_skb(fq->q.fragments);
fq->q.fragments = head;
}
WARN_ON(head == NULL);
WARN_ON(FRAG6_CB(head)->offset != 0);
payload_len = ((head->data - skb_network_header(head)) -
sizeof(struct ipv6hdr) + fq->q.len -
sizeof(struct frag_hdr));
if (payload_len > IPV6_MAXPLEN)
goto out_oversize;
if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC))
goto out_oom;
if (skb_has_frags(head)) {
struct sk_buff *clone;
int i, plen = 0;
if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL)
goto out_oom;
clone->next = head->next;
head->next = clone;
skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
skb_frag_list_init(head);
for (i=0; i<skb_shinfo(head)->nr_frags; i++)
plen += skb_shinfo(head)->frags[i].size;
clone->len = clone->data_len = head->data_len - plen;
head->data_len -= clone->len;
head->len -= clone->len;
clone->csum = 0;
clone->ip_summed = head->ip_summed;
atomic_add(clone->truesize, &fq->q.net->mem);
}
nhoff = fq->nhoffset;
skb_network_header(head)[nhoff] = skb_transport_header(head)[0];
memmove(head->head + sizeof(struct frag_hdr), head->head,
(head->data - head->head) - sizeof(struct frag_hdr));
head->mac_header += sizeof(struct frag_hdr);
head->network_header += sizeof(struct frag_hdr);
skb_shinfo(head)->frag_list = head->next;
skb_reset_transport_header(head);
skb_push(head, head->data - skb_network_header(head));
atomic_sub(head->truesize, &fq->q.net->mem);
for (fp=head->next; fp; fp = fp->next) {
head->data_len += fp->len;
head->len += fp->len;
if (head->ip_summed != fp->ip_summed)
head->ip_summed = CHECKSUM_NONE;
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
atomic_sub(fp->truesize, &fq->q.net->mem);
}
head->next = NULL;
head->dev = dev;
head->tstamp = fq->q.stamp;
ipv6_hdr(head)->payload_len = htons(payload_len);
IP6CB(head)->nhoff = nhoff;
if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_partial(skb_network_header(head),
skb_network_header_len(head),
head->csum);
rcu_read_lock();
IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
rcu_read_unlock();
fq->q.fragments = NULL;
return 1;
out_oversize:
if (net_ratelimit())
printk(KERN_DEBUG "ip6_frag_reasm: payload len = %d\n", payload_len);
goto out_fail;
out_oom:
if (net_ratelimit())
printk(KERN_DEBUG "ip6_frag_reasm: no memory for reassembly\n");
out_fail:
rcu_read_lock();
IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
rcu_read_unlock();
return -1;
}
